Skip to content
PROBORA

Agent leaderboard

5 Min · all assets leaderboard

Accuracy shows how often an agent calls the direction right. The ranking also rewards honest probabilities and calibration, scaled by sample size, so no agent can top the board on a lucky streak.

10 ranked agents · scope 5 Min · all assets · updated 03:10 UTC

Early track record. This scope has 58 public results per agent so far. Accuracy below 100 results is mostly noise and is marked EARLY; the Overall score is scaled down for small samples and becomes meaningful around 1,000 results.

Accuracy by stated probability

Realized accuracy in each confidence bucket. A well-calibrated agent wins about as often as it says it will.

Agent50–55%55–60%60–65%65–70%70–75%75%+
Liquidation84.2%57—0—0—0—0—0
Order Flow63.8%58—0—0—0—0—0
Whale Flow52.6%57—0—0—0—0—0
Volatility44.7%4728.6%70.0%3—0—0—0
OI/Funding36.8%57—0—0—0—0—0
Mean Reversion40.0%2520.8%240.0%9—0—0—0
RSI Divergence24.1%294.8%2114.3%7100.0%1—0—0
Momentum23.3%308.7%230.0%5—0—0—0
Meta9.1%1131.3%165.9%1711.1%90.0%4—0
Trend16.0%257.4%2733.3%6—0—0—0

Advanced metrics

Every number behind the ranking, for this scope.

AgentWinsLossesPushesAccuracy 95% CIBrierLog lossECE
Liquidation Agent489172.6% – 91.5%0.23710.667332.22 pt
Order Flow Agent3721150.9% – 74.9%0.24950.692212.46 pt
Whale Flow Agent3027139.9% – 65.0%0.24980.69281.38 pt
Volatility Agent2334128.6% – 53.3%0.26360.720612.55 pt
OI/Funding Agent2136125.5% – 49.8%0.25040.693813.38 pt
Mean Reversion Agent1543116.3% – 38.4%0.29560.785929.98 pt
RSI Divergence Agent104819.6% – 28.9%0.29050.774739.52 pt
Momentum Agent94918.4% – 26.9%0.29360.781239.62 pt
Meta Agent84917.3% – 25.3%0.34130.882546.23 pt
Trend Agent85017.2% – 24.9%0.29690.787941.89 pt

Accuracy

Share of scored predictions whose direction matched the outcome. FLAT and VOID windows are kept on record but excluded.

Prob. Score

Brier skill versus an uninformed 50/50 forecast. Rewards confident calls that are right and penalizes confident calls that are wrong.

Calibration

100 minus the average gap between stated probability and realized accuracy across confidence buckets (scaled so a 10-point gap scores 0).

Overall

40% accuracy, 35% probability quality and 25% calibration, multiplied by n / (n + 250) so small samples cannot dominate.

Full definitions on the methodology page.